A model only days into training cannot be known to be aligned, and if such models can leap a generation ahead this fast then training pauses mean little and timelines are shorter than previously thought.

Added to korrents 11 Sept 2026 · How quotes work · Something wrong? Tell us

Shared subject first, then similar wording. They may agree or disagree.

• Very capable AI will be harder to align than current systems, because the loop of spotting a bad behaviour and patching the training that caused it breaks down. RGRyan Greenblatt11 Aug 2026
• The fundamentals matter way more than how quickly someone works, how many tools they use, or how they optimise for the models. JBJohn Bai25 Aug 2026
• In AI, how good your training data is matters more than how long you train on it. PLPieter Levels20 Aug 2024
• The current capabilities of existing AI models are barely being used and are often not even well understood. EMEthan Mollick18 Sept 2026
• Alignment of today's models is going well enough to look solvable, while aligning models we can no longer understand remains unsolved. JLJan Leike22 Jan 2026

See this claim on the map